Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "Per" followed by other characters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Per" or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.85
    INESS
    -0.79
    DERR
    -0.77
    å¸
    -0.74
    ATIONAL
    -0.70
     Raleigh
    -0.68
     Tycoon
    -0.68
     Lazarus
    -0.67
    orld
    -0.67
    è¦ļéĨĴ
    -0.66
    POSITIVE LOGITS
     capita
    1.21
    due
    1.20
    secut
    1.19
    ipher
    1.18
    ceptions
    1.17
    iod
    1.14
    pet
    1.09
    forming
    1.09
    secution
    1.08
    uvian
    1.06
    Act Density 0.016%

    No Known Activations